AI Threat Alert
AI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 851 results — Medium severity CVE-2025-2953 PyTorch: DoS via mkldnn_max_pool2d resource leak 5.5 0.2% pytorch Mar 30 MEDI E CVE-2025-26265 openairinterface5g: segfault enables DoS via crafted UE message 6.5 0.4% openairinterface5g Mar 27 MEDI E CVE-2025-0508 SageMaker SDK: MD5 collision silently replaces ML workflows 5.9 0.2% sagemaker Mar 20 MEDI E CVE-2024-7045 open-webui: missing authz exposes admin prompts 4.3 0.4% open-webui Mar 20 MEDI E CVE-2024-7035 Open WebUI: CSRF wipes RAG DB and AI memories via GET 6.9 0.2% open-webui Mar 20 MEDI E CVE-2024-7046 Open WebUI: missing authz leaks admin credentials 4.3 0.4% open-webui Mar 20 MEDI E CVE-2024-7044 Open WebUI: Stored XSS via file upload, session hijack 6.8 0.5% open-webui Mar 20 MEDI E CVE-2024-7034 open-webui: path traversal allows arbitrary file write/RCE 6.5 2.5% open-webui Mar 20 MEDI E CVE-2024-7033 open-webui: path traversal allows file write and RCE 6.5 1.1% open-webui Mar 20 MEDI E CVE-2024-12910 llama-index: DoS via infinite recursion in web reader 5.9 0.6% llama-index Mar 20 MEDI GHSA-564p-rx2q-4c8v BentoML: open redirect exposes ML teams to phishing 6.1 — bentoml Mar 20 MEDI E CVE-2025-1474 MLflow: passwordless accounts enable persistent backdoor 5.5 0.3% mlflow Mar 20 MEDI E CVE-2024-8021 Gradio: open redirect exposes AI demo users to phishing 6.1 0.7% gradio Mar 20 MEDI E CVE-2024-6838 MLflow: unconstrained input causes UI denial of service 5.3 0.6% mlflow Mar 20 MEDI E CVE-2024-6577 TorchServe: unverified S3 bucket exposes benchmark data 6.3 0.4% torchserve Mar 20 MEDI E CVE-2024-12217 Gradio: NTFS ADS bypass exposes blocked file paths 5.3 0.6% gradio Mar 20 MEDI E CVE-2024-10940 langchain-core: file read via prompt template inputs 5.3 0.4% langchain-core Mar 20 MEDI E CVE-2025-29770 vLLM: DoS via unbounded grammar cache exhausts disk 6.5 0.4% vllm Mar 19 MEDI E CVE-2025-1944 picklescan: ZIP spoof lets malicious PyTorch models bypass scan 6.5 0.3% picklescan Mar 10 MEDI CVE-2025-1979 Ray: Redis password exposed via plaintext logging 6.4 0.2% ray Mar 6 Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
Need deeper analysis?
Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.
Start 14-Day Free Trial